Intestinal typing method, device and medium based on intestinal microflora structure

Abstract

The application relates to the technical field of intestinal typing, and discloses an intestinal typing method based on intestinal microorganism flora structure, which comprises the following steps: acquiring intestinal flora sequencing data; the intestinal flora sequencing data comprises intestinal flora 16s amplicon data and metagenome sequencing data; performing quality control and species annotation analysis on the intestinal flora sequencing data to obtain first relative abundance information of sample intestinal flora; screening according to the first relative abundance information and a chi-square verification method to obtain intestinal flora characteristic data; and inputting the intestinal flora characteristic data into a preset intestinal type prediction model to perform intestinal type prediction. The 16s amplicon and metagenome sequencing data are processed and analyzed to obtain intestinal flora characteristic data, and a preset intestinal type prediction model is used to perform intestinal flora typing to predict the intestinal type. Compared with a clustering method, a machine learning method can improve the efficiency and accuracy of intestinal type identification, can perform intestinal type identification on single and multiple samples, and is not limited to single-source samples.

Description

Technical Field

[0001] This application relates to the field of intestinal typing technology, and in particular to an intestinal typing method, device and medium based on the structure of intestinal microbiota. Background Technology

[0002] Recent studies on gut microbiota have extensively demonstrated the differences in gut microbiota among individuals and their correlation with health status. In terms of microbial composition, our understanding of gut microbiota has evolved from the phylum level to higher-resolution taxonomic units such as genus and species. However, the gut microbiota is a continuous and unified entity composed of different microbial communities, with an extremely complex structure. Therefore, determining the structure of the gut microbiota community and the underlying mechanisms is crucial for a better understanding of human health or disease status. Subsequent research on factors influencing gut type has shown that gut type is not related to sex, age, or weight, but is related to dietary habits; medications and health / disease status are also associated with microbiota structure. Therefore, mapping gut microbiota structure characteristics similar to "gut type" can serve as an effective auxiliary tool for health status assessment and treatment follow-up.

[0003] In 2011, the European Molecular Biology Laboratory (EMBL) first proposed the concept of "enteric typing," which is based on unsupervised clustering of bacterial colonies to classify individuals, with different categories defined as specific enteric types. Researchers identified three enteric types from 33 human fecal samples. These three enteric types can be identified by variations in the abundance of one of three bacterial genera: Bacteroides (enteric type 1), Prevotella (enteric type 2), and Ruminococcus (enteric type 3). The same phenomenon was also observed in two other populations (154 Americans and 85 Danes). Currently, the main method for entering type identification is to classify the tested population using unsupervised clustering to determine the enteric type of the sample. However, clustering methods often require a certain sample size, resulting in low efficiency. Furthermore, the algorithm's robustness is compromised due to uncertainties in sample size and the number of clusters. This method is also suitable for single-source sequencing data, and the stability of results from multi-source data is unclear.

[0004] Therefore, how to improve the efficiency and accuracy of intestinal type identification, and how to identify intestinal types for both single and multiple samples, and not be limited to samples from a single source, is a problem that urgently needs to be solved by those skilled in the art. Summary of the Invention

[0005] The purpose of this application is to provide a method, device and medium for intestinal typing based on the structure of intestinal microbiota, which can improve the efficiency and accuracy of intestinal typing identification, and can identify intestinal types of both single and multiple samples, and is not limited to samples from a single source.

[0006] To address the aforementioned technical problems, this application provides a method for intestinal typing based on the structure of the gut microbiota, comprising:

[0007] Acquire gut microbiota sequencing data; the gut microbiota sequencing data includes gut microbiota 16S amplicon data and metagenomic sequencing data;

[0008] The gut microbiota sequencing data were subjected to quality control and species annotation analysis to obtain the first relative abundance information of the gut microbiota in the sample.

[0009] Gut microbiota characteristic data are obtained by screening based on the first relative abundance information and the chi-square verification method.

[0010] The gut microbiota characteristic data are input into a preset gut type prediction model to predict the gut type.

[0011] Optionally, if the gut microbiota sequencing data is the metagenomic sequencing data, the step of performing quality control and species annotation analysis on the gut microbiota sequencing data to obtain the first relative abundance information of the sample gut microbiota includes:

[0012] The metagenomic sequencing data is subjected to quality control to remove adapters and filter out low-quality bases.

[0013] The host sequence is removed from the quality-controlled metagenomic sequencing data to obtain the metagenomic DNA sequence;

[0014] Species annotation was performed on the metagenomic DNA sequences;

[0015] The annotation results were corrected to obtain the absolute abundance information of the gut microbiota;

[0016] The absolute abundance information of the gut microbiota at the genus level is extracted and homogenized to obtain the first relative abundance information of the gut microbiota.

[0017] Optionally, if the gut microbiota sequencing data is the gut microbiota 16S amplicon data, the step of performing quality control and species annotation analysis on the gut microbiota sequencing data to obtain the first relative abundance information of the sample gut microbiota includes:

[0018] If the gut microbiota 16S amplicon data is paired-end sequencing data, then the paired-end sequence files are merged, primers are removed from the merged sequence files, and quality control is performed.

[0019] The sequence files after quality control are deredundanted and dechirped, and clustered into operational classification units.

[0020] By comparing with the database, species annotation is performed on the operational taxonomic units to obtain the absolute abundance information of the gut microbiota.

[0021] The absolute abundance information of the gut microbiota at the genus level is extracted and homogenized to obtain the first relative abundance information of the gut microbiota.

[0022] Optionally, the step of filtering based on the first relative abundance information and the chi-square verification method to obtain gut microbiota characteristic data includes:

[0023] The correlation between the first relative abundance information and the gut type is calculated using the chi-square verification method in the sklearn Python library. Significant features with a correlation less than a preset value are used as the gut microbiota feature data.

[0024] Optionally, before inputting the gut microbiota feature data into a preset gut type prediction model for gut type prediction, the method further includes:

[0025] Fecal samples were selected as the experimental data.

[0026] The experimental data were subjected to quality control and species annotation analysis to obtain the second relative abundance information of the gut microbiota of the samples. Significant features were then screened based on the second relative abundance information and the chi-square verification method to construct a sample set.

[0027] The sample set is randomly divided into a training set and a test set according to a preset ratio;

[0028] The training set is trained using each machine learning algorithm to construct a classification model corresponding to each machine learning algorithm. The performance of each classification model is verified using the test set, and the classification model with the best performance is selected as the preset intestinal shape prediction model.

[0029] Optionally, the step of verifying the performance of each classification model using the test set and selecting the best-performing classification model as the preset gut type prediction model includes:

[0030] The accuracy of each classification model is calculated using the test set;

[0031] The classification model with the highest accuracy is used as the preset intestinal type prediction model.

[0032] Optionally, the step of verifying the performance of each classification model using the test set and selecting the best-performing classification model as the preset gut type prediction model includes:

[0033] Plot the AUROC diagrams for each of the classification models using the test set;

[0034] The performance of each classification model is compared based on the AUROC plot, and the classification model with the best performance is selected as the preset intestinal type prediction model.

[0035] This application also provides an intestinal typing device based on the structure of the gut microbiota, comprising:

[0036] The acquisition module is used to acquire gut microbiota sequencing data; the gut microbiota sequencing data includes gut microbiota 16S amplicon data and metagenomic sequencing data;

[0037] The first relative abundance information determination module is used to perform quality control and species annotation analysis on the gut microbiota sequencing data to obtain the first relative abundance information of the sample gut microbiota.

[0038] The screening module is used to screen gut microbiota characteristic data based on the first relative abundance information and the chi-square verification method.

[0039] The prediction module is used to input the gut microbiota characteristic data into a preset gut type prediction model to predict the gut type.

[0040] This application also provides an intestinal typing device based on the structure of intestinal microbiota, including a memory for storing computer programs;

[0041] A processor is used to implement the steps of the gut microbiota-based intestinal typing method when executing the computer program.

[0042] This application also provides a computer-readable storage medium, characterized in that a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, it implements the steps of the intestinal typing method based on the intestinal microbiota structure.

[0043] This application provides a gut microbiota-based enterotype typing method, comprising: acquiring gut microbiota sequencing data; the gut microbiota sequencing data including gut microbiota 16S amplicon data and metagenomic sequencing data; performing quality control and species annotation analysis on the gut microbiota sequencing data to obtain the first relative abundance information of the sample gut microbiota; screening based on the first relative abundance information and chi-square validation to obtain gut microbiota characteristic data; and inputting the gut microbiota characteristic data into a preset enterotype prediction model for enterotype prediction. This application can process and analyze 16S amplicon data and metagenomic sequencing data to obtain gut microbiota characteristic data, and use a preset enterotype prediction model to type the gut microbiota to predict enterotype. Compared with clustering methods, machine learning methods can improve the efficiency and accuracy of enterotype identification, and can identify enterotypes for single samples or multiple samples, and are not limited to samples from a single source.

[0044] The beneficial effects and methods of the intestinal typing device and medium based on the intestinal microbiota structure provided in this application are as described above. Attached Figure Description

[0045] To more clearly illustrate the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0046] Figure 1 A flowchart illustrating an intestinal typing method based on gut microbiota structure provided in this application embodiment;

[0047] Figure 2 An AUROC diagram of four classification models provided in this application embodiment;

[0048] Figure 3 A structural diagram of an intestinal typing device based on the intestinal microbiota structure provided in this application embodiment;

[0049] Figure 4 This is a structural diagram of another intestinal typing device based on the gut microbiota structure provided in an embodiment of this application. Detailed Implementation

[0050] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the protection scope of this application.

[0051] The core of this application is to provide a method, device, and medium for intestinal typing based on the structure of the gut microbiota.

[0052] To enable those skilled in the art to better understand the present application, the present application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0053] Figure 1 A flowchart of an intestinal typing method based on intestinal microbiota structure provided in this application embodiment is shown below. Figure 1 As shown, intestinal typing methods include:

[0054] S10: Obtain gut microbiota sequencing data; gut microbiota sequencing data includes gut microbiota 16S amplicon data and metagenomic sequencing data.

[0055] S11: Perform quality control and species annotation analysis on the gut microbiota sequencing data to obtain the first relative abundance information of the gut microbiota in the sample.

[0056] If the gut microbiota sequencing data is metagenomic sequencing data, quality control and species annotation analysis are performed on the gut microbiota sequencing data to obtain the first relative abundance information of the sample gut microbiota. This includes: quality control of the metagenomic sequencing data to remove adapters and filter low-quality bases; removal of host sequences from the quality-controlled metagenomic sequencing data to obtain metagenomic DNA sequences; species annotation of the metagenomic DNA sequences; correction of the annotation results to obtain the absolute abundance information of the gut microbiota; extraction and homogenization of the absolute abundance information of the gut microbiota at the genus level to obtain the first relative abundance information of the gut microbiota.

[0057] The specific steps are as follows: quality control of the metagenomic data of the samples to be genotyped; use FASTP software to automatically find and remove adapters from the metagenomic data and filter low-quality bases; use Kneaddata software to remove host sequences; use Kraken2 software to annotate the quality control and host-removed metagenomic DNA sequences for species; use Bracken to correct the Kraken2 annotation results to obtain the absolute abundance information of the gut microbiota; extract the absolute abundance information of the gut microbiota at the genus level and homogenize it to obtain the first relative abundance information of the gut microbiota.

[0058] If the gut microbiota sequencing data is gut microbiota 16S amplicon data, quality control and species annotation analysis are performed on the gut microbiota sequencing data to obtain the first relative abundance information of the sample gut microbiota. This includes: if the gut microbiota 16S amplicon data is paired-end sequencing data, merging the paired-end sequence files, removing primers from the merged sequence files and performing quality control; deduplicating and removing chimeras from the quality-controlled sequence files to cluster them into operational taxonomic units; performing species annotation on the operational taxonomic units by comparing them with a database to obtain the absolute abundance information of the gut microbiota; extracting the absolute abundance information of the gut microbiota at the genus level and homogenizing it to obtain the first relative abundance information of the gut microbiota.

[0059] The specific steps are as follows: Data preprocessing: If the 16S amplicon data of the sample to be genotyped is paired-end sequencing data, then merge the paired-end sequence files, and then remove primers and perform quality control on the sequence files (filtering low-quality reads and removing low-quality bases at the ends); OTU clustering: perform redundancy removal, chimera removal, and clustering into Operational Taxonomic Units (OTUs) on the quality-controlled sequence files; Species annotation: perform species annotation on OTUs by comparing with the database to obtain the absolute abundance information of gut microbiota; extract the absolute abundance information of gut microbiota at the genus level and homogenize it to obtain the first relative abundance information of gut microbiota.

[0060] S12: Screening is performed based on the first relative abundance information and the chi-square verification method to obtain gut microbiota characteristic data.

[0061] The chi-square test method in the sklearn Python library is used to calculate the correlation between the first relative abundance information and the gut type. Significant features with a correlation less than a preset value are used as gut microbiota feature data. For example, significant features with a p-value less than 0.05 can be selected as gut microbiota feature data.

[0062] S13: Input gut microbiota characteristic data into the preset gut type prediction model to predict gut type.

[0063] In this application embodiment, the type of preset gut shape prediction model is not specifically limited. The preset gut shape prediction model can be a model constructed and optimized by machine learning algorithms such as logistic regression, KNN, random forest and XGBoost through K-fold cross-validation.

[0064] This application provides a gut microbiota-based enterotyping method, comprising: acquiring gut microbiota sequencing data; the gut microbiota sequencing data including 16S amplicon data and metagenomic sequencing data; performing quality control and species annotation analysis on the gut microbiota sequencing data to obtain the first relative abundance information of the sample's gut microbiota; filtering based on the first relative abundance information and chi-square validation to obtain gut microbiota characteristic data; and inputting the gut microbiota characteristic data into a preset enterotype prediction model for enterotype prediction. This application can process and analyze 16S amplicon data and metagenomic sequencing data to obtain gut microbiota characteristic data, and use a preset enterotype prediction model to type the gut microbiota to predict enterotype. Compared with clustering methods, machine learning methods can improve the efficiency and accuracy of enterotype identification, enabling enterotype identification for both single and multiple samples, and is not limited to samples from a single source. Furthermore, the process of this application is simple to deploy and easy to use; only the relevant computing nodes need to be deployed to complete the entire analysis process.

[0065] Based on the above embodiments, before inputting gut microbiota feature data into a preset gut type prediction model for gut type prediction, this application embodiment further includes: selecting fecal samples as experimental data; performing quality control and species annotation analysis on the experimental data to obtain the second relative abundance information of the gut microbiota in the samples, and screening significant features based on the second relative abundance information and the chi-square verification method to construct a sample set; randomly dividing the sample set into a training set and a test set according to a preset ratio; training the training set using each machine learning algorithm to construct the classification model corresponding to each machine learning algorithm, and verifying the performance of each classification model using the test set, and using the classification model with the best performance as the preset gut type prediction model.

[0066] For ease of understanding, the following example illustrates the process. 425 fecal samples (184 healthy individuals and 241 autistic patients) were selected as experimental data. Quality control and species annotation analysis were performed on the experimental data to obtain the second relative abundance information of the gut microbiota. The chi-square validation method (chi2) in the sklearn Python library was used to calculate the correlation between the second relative abundance information of bacterial genera and intestinal type. Six significant features were selected to construct a sample set. The six significant features included: *Blautia*, *Collinsella*, *Bifidobacterium*, *Bacteroides*, *Phocaeicola* (a new genus classified in 2009 by the order Bacteroidetes), and *Prevotella*. The 425 samples were randomly divided into training and test sets at a 3:1 ratio. Logistic Regression, KNN (K-Nearest Neighbor), and Random Forest were used respectively. Four machine learning algorithms, including Forest and XGBoost, were used to construct and optimize models using K-fold cross-validation (using the training set to build the classification model and the test set to validate the performance of the classification model); the best-performing classification model was then used as the preset gut shape prediction model.

[0067] Based on the above embodiments, this application embodiment uses a test set to verify the performance of each classification model, and selects the classification model with the best performance as the preset intestinal type prediction model, including: calculating the accuracy of each classification model using the test set; and selecting the classification model with the highest accuracy as the preset intestinal type prediction model. Alternatively, the AUROC plot of each classification model is plotted using the test set; the performance of each classification model is compared based on the AUROC plot, and the classification model with the best performance is selected as the preset intestinal type prediction model.

[0068] Specifically, we introduce accuracy and coefficient of determination (R²). 2The mean squared error (MSE) and mean absolute error (MAE) parameters were used to evaluate the classification performance of the four models on the test set. The accuracy value represents the model's precision; a higher accuracy value indicates better classification ability. Alternatively, an AUROC plot can be used to compare the performance of each classification model. Table 1 shows the performance evaluation of the classification models built using the four machine learning algorithms. Figure 2 An AUROC diagram of a four-classification model provided in an embodiment of this application.

[0069] Table 1 shows the performance evaluation of the classification models built using four machine learning algorithms.

[0070] Logistics Regression KNN Random Forest XGBoost Mean Absolute Error 0.2617 0.2243 0.215 0.3178 Mean Squared Error 0.486 0.3925 0.3832 0.5794 R^2 0.3491 0.4743 0.4868 0.2239 Accuracy 0.8505 0.8598 0.8692 0.8131

[0071] Table 1 shows that the classification model built using the Random Forest machine learning algorithm has the highest accuracy. Figure 2 As shown, the classification model built using the Random Forest machine learning algorithm has the highest AUC value. Of course, classification models built using other machine learning algorithms can also be used as preset gut shape prediction models.

[0072] Based on the above embodiments, for ease of understanding, the following example illustrates how to predict the intestinal type of a sample using a preset intestinal type prediction model.

[0073] If the sample to be tested is metagenomic sequencing data, quality control and species annotation analysis are performed on the metagenomic sequencing data to obtain the relative abundance information of the gut microbiota of the sample, as detailed in the quality control and species annotation analysis methods of the above embodiments; significant feature information is extracted from the relative abundance information of the sample to be tested to construct a gut type prediction sample set; the sample set is input into a preset gut type prediction model to obtain the gut type prediction result. Of course, the sample to be tested in this embodiment can be fecal sample data of autistic patients, fecal sample data of healthy individuals, and fecal sample data of other patients. It is not limited to using metagenomic data; 16S amplicon data can also be selected.

[0074] In the above embodiments, the enterotyping method based on the gut microbiota structure has been described in detail. This application also provides embodiments of an enterotyping device based on the gut microbiota structure. It should be noted that this application describes the embodiments of the device from two perspectives: one is based on the functional modules, and the other is based on the hardware.

[0075] Figure 3 A structural diagram of an intestinal typing device based on the intestinal microbiota structure provided in this application embodiment is shown below. Figure 3 As shown, the intestinal typing device includes:

[0076] Module 10 is used to acquire gut microbiota sequencing data; the gut microbiota sequencing data includes gut microbiota 16S amplicon data and metagenomic sequencing data;

[0077] The first relative abundance information determination module 11 is used to perform quality control and species annotation analysis on gut microbiota sequencing data to obtain the first relative abundance information of the gut microbiota in the sample.

[0078] The screening module 12 is used to screen gut microbiota characteristic data based on the first relative abundance information and the chi-square verification method.

[0079] The prediction module 13 is used to input gut microbiota characteristic data into a preset gut type prediction model to predict gut type.

[0080] Based on the above embodiments, as a preferred embodiment, the first relative abundance information determination module includes:

[0081] The first quality control unit is used to perform quality control on metagenomic sequencing data to remove adapters and filter out low-quality bases in the metagenomic sequencing data.

[0082] The first removal unit is used to remove the host sequence from the quality-controlled metagenomic sequencing data to obtain the metagenomic DNA sequence.

[0083] The first species annotation unit is used for species annotation of metagenomic DNA sequences;

[0084] The correction unit is used to correct the annotation results and obtain the absolute abundance information of the gut microbiota.

[0085] The first relative abundance information determination unit is used to extract the absolute abundance information of gut microbiota at the genus level and homogenize it to obtain the first relative abundance information of gut microbiota.

[0086] Based on the above embodiments, as a preferred embodiment, the first relative abundance information determination module includes:

[0087] The second quality control unit is used to merge paired-end sequence files if the gut microbiota 16S amplicon data are paired-end sequencing data, remove primers from the merged sequence files and perform quality control.

[0088] The second removal unit is used to remove redundancy and chimerism from the quality-controlled sequence files and cluster them into operation classification units.

[0089] The second species annotation unit is used to annotate the operational taxonomic units by comparing them with the database, so as to obtain the absolute abundance information of the gut microbiota.

[0090] The second relative abundance information determination unit is used to extract the absolute abundance information of gut microbiota at the genus level and homogenize it to obtain the first relative abundance information of gut microbiota.

[0091] Based on the above embodiments, as a preferred embodiment, the screening module includes:

[0092] The filtering unit is used to calculate the correlation between the first relative abundance information and the gut type using the chi-square verification method in the sklearn python library, and to take significant features with a correlation less than a preset value as gut microbiota feature data.

[0093] Based on the above embodiments, as a preferred embodiment, it further includes:

[0094] The selection module is used to select fecal samples as experimental data.

[0095] The module is used to perform quality control and species annotation analysis on experimental data to obtain the second relative abundance information of the gut microbiota of the samples, and to screen significant features based on the second relative abundance information and the chi-square validation method to construct the sample set;

[0096] The partitioning module is used to randomly divide the sample set into a training set and a test set according to a preset ratio;

[0097] The module for determining the pre-defined intestinal shape prediction model is used to train the training set using each machine learning algorithm to construct the classification model corresponding to each machine learning algorithm, and to verify the performance of each classification model using the test set, and to select the classification model with the best performance as the pre-defined intestinal shape prediction model.

[0098] Based on the above embodiments, as a preferred embodiment, the preset intestinal pattern prediction model determination module includes:

[0099] The computation unit is used to calculate the accuracy of each classification model using the test set;

[0100] The first preset intestinal type prediction model determination unit is used to select the classification model with the highest accuracy as the preset intestinal type prediction model.

[0101] Based on the above embodiments, as a preferred embodiment, the preset intestinal pattern prediction model determination module includes:

[0102] The plotting unit is used to plot the AUROC diagram of each classification model using the test set;

[0103] The second preset intestinal type prediction model determination unit is used to compare the performance of each classification model based on the AUROC diagram, and select the classification model with the best performance as the preset intestinal type prediction model.

[0104] Since the embodiments of the apparatus and the embodiments of the method correspond to each other, please refer to the description of the embodiments of the method for the embodiments of the apparatus, which will not be repeated here.

[0105] This application provides an intestinal microbiota-based enterotyping device that acquires intestinal microbiota sequencing data, including 16S amplicon data and metagenomic sequencing data. The device performs quality control and species annotation analysis on the intestinal microbiota sequencing data to obtain the first relative abundance information of the sample's intestinal microbiota. Based on the first relative abundance information and chi-square verification, it filters the data to obtain intestinal microbiota characteristic data. The intestinal microbiota characteristic data is then input into a preset enterotype prediction model for enterotype prediction. This application can process and analyze 16S amplicon data and metagenomic sequencing data to obtain intestinal microbiota characteristic data, and use a preset enterotype prediction model to type the intestinal microbiota to predict enterotype. Compared to clustering methods, machine learning methods can improve the efficiency and accuracy of enterotype identification, enabling intestinal type identification for both single and multiple samples, and is not limited to samples from a single source. Furthermore, the deployment process of this application is simple and easy to use; only the relevant computing nodes need to be deployed to complete the entire analysis process.

[0106] Figure 4 A structural diagram of another intestinal typing device based on the gut microbiota structure provided in this application embodiment is shown below. Figure 4 As shown, the gut microbiota-based intestinal typing device includes: a memory 20 for storing computer programs;

[0107] The processor 21 is used to execute a computer program to implement the steps of the intestinal typing method based on the intestinal microbiota structure as described in the above embodiments.

[0108] The gut microbiota typing device provided in this embodiment can be, but is not limited to, smartphones, tablets, laptops, or desktop computers.

[0109] The processor 21 may include one or more processing cores, such as a quad-core processor or an octa-core processor. The processor 21 may be implemented using at least one of the following hardware forms: Digital Signal Processor (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). The processor 21 may also include a main processor and a coprocessor. The main processor, also known as the Central Processing Unit (CPU), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, the processor 21 may integrate a Graphics Processing Unit (GPU), which is responsible for rendering and drawing the content to be displayed on the screen. In some embodiments, the processor 21 may also include an Artificial Intelligence (AI) processor, which is used to handle computational operations related to machine learning.

[0110] The memory 20 may include one or more computer-readable storage media, which may be non-transitory. The memory 20 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices or flash memory devices. In this embodiment, the memory 20 is used to store at least the following computer program 201, which, after being loaded and executed by the processor 21, is capable of implementing the relevant steps of the gut microbiota-based intestinal typing method disclosed in any of the foregoing embodiments. In addition, the resources stored in the memory 20 may also include an operating system 202 and data 203, and the storage method may be temporary or permanent. The operating system 202 may include Windows, Unix, Linux, etc. The data 203 may include, but is not limited to, gut microbiota 16S amplicon data and metagenomic sequencing data.

[0111] In some embodiments, the gut microbiota-based intestinal typing device may further include a display screen 22, an input / output interface 23, a communication interface 24, a power supply 25, and a communication bus 26.

[0112] Those skilled in the art will understand that Figure 4 The structures shown do not constitute a limitation on gut microbiota-based intestinal typing devices and may include more or fewer components than those shown.

[0113] The gut microbiota-based enterotyping device provided in this application includes a memory and a processor. When the processor executes the program stored in the memory, it can perform the following methods: acquiring gut microbiota sequencing data; the gut microbiota sequencing data includes gut microbiota 16S amplicon data and metagenomic sequencing data; performing quality control and species annotation analysis on the gut microbiota sequencing data to obtain the first relative abundance information of the sample gut microbiota; screening according to the first relative abundance information and the chi-square verification method to obtain gut microbiota characteristic data; and inputting the gut microbiota characteristic data into a preset enterotype prediction model for enterotype prediction.

[0114] Finally, this application also provides an embodiment corresponding to a computer-readable storage medium. The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps described in the intestinal typing method based on the gut microbiota structure of the above-described method embodiments.

[0115] It is understood that if the methods in the above embodiments are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and executes all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0116] The foregoing provides a detailed description of the intestinal microbiota typing method, apparatus, and medium based on the structure of the intestinal microbiota provided in this application. The various embodiments in the specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to in the method section. It should be noted that those skilled in the art can make several improvements and modifications to this application without departing from the principles of this application, and these improvements and modifications also fall within the protection scope of the claims of this application.

[0117] It should also be noted that, in this specification, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

Claims

1. A method for gut microbiota typing based on gut microbiota structure, characterized in that, include: Acquire gut microbiota sequencing data; the gut microbiota sequencing data includes gut microbiota 16S amplicon data and metagenomic sequencing data; The gut microbiota sequencing data were subjected to quality control and species annotation analysis to obtain the first relative abundance information of the gut microbiota in the sample. Gut microbiota characteristic data are obtained by screening based on the first relative abundance information and the chi-square verification method. The gut microbiota characteristic data is input into a preset gut type prediction model to predict the gut type. If the gut microbiota sequencing data is the metagenomic sequencing data, the quality control and species annotation analysis of the gut microbiota sequencing data to obtain the first relative abundance information of the sample gut microbiota includes: The metagenomic sequencing data is subjected to quality control to remove adapters and filter out low-quality bases. The host sequence is removed from the quality-controlled metagenomic sequencing data to obtain the metagenomic DNA sequence; Species annotation was performed on the metagenomic DNA sequences; The annotation results were corrected to obtain the absolute abundance information of the gut microbiota; The absolute abundance information of gut microbiota at the genus level is extracted and homogenized to obtain the first relative abundance information of gut microbiota. If the gut microbiota sequencing data is the gut microbiota 16S amplicon data, the step of performing quality control and species annotation analysis on the gut microbiota sequencing data to obtain the first relative abundance information of the sample gut microbiota includes: If the gut microbiota 16S amplicon data is paired-end sequencing data, then the paired-end sequence files are merged, primers are removed from the merged sequence files, and quality control is performed. The sequence files after quality control are deredundanted and dechirped, and clustered into operational classification units. By comparing with the database, species annotation is performed on the operational taxonomic units to obtain the absolute abundance information of the gut microbiota. The absolute abundance information of the gut microbiota at the genus level is extracted and homogenized to obtain the first relative abundance information of the gut microbiota.

2. The intestinal typing method based on intestinal microbiota structure according to claim 1, characterized in that, The step of filtering based on the first relative abundance information and the chi-square verification method to obtain gut microbiota characteristic data includes: The correlation between the first relative abundance information and the gut type is calculated using the chi-square verification method in the sklearn Python library. Significant features with a correlation less than a preset value are used as the gut microbiota feature data.

3. The intestinal type typing method based on intestinal microbiota structure according to claim 1, characterized in that, Before inputting the gut microbiota feature data into a preset gut type prediction model for gut type prediction, the method further includes: Fecal samples were selected as the experimental data. The experimental data were subjected to quality control and species annotation analysis to obtain the second relative abundance information of the gut microbiota of the samples. Significant features were then screened based on the second relative abundance information and the chi-square verification method to construct a sample set. The sample set is randomly divided into a training set and a test set according to a preset ratio; The training set is trained using each machine learning algorithm to construct a classification model corresponding to each machine learning algorithm. The performance of each classification model is verified using the test set, and the classification model with the best performance is selected as the preset intestinal shape prediction model.

4. The intestinal type typing method based on intestinal microbiota structure according to claim 3, characterized in that, The step of verifying the performance of each classification model using the test set and selecting the best-performing classification model as the preset gut type prediction model includes: The accuracy of each classification model is calculated using the test set; The classification model with the highest accuracy is used as the preset intestinal type prediction model.

5. The intestinal type typing method based on intestinal microbiota structure according to claim 3, characterized in that, The step of verifying the performance of each classification model using the test set and selecting the best-performing classification model as the preset gut type prediction model includes: Plot the AUROC diagrams for each of the classification models using the test set; The performance of each classification model is compared based on the AUROC plot, and the classification model with the best performance is selected as the preset intestinal type prediction model.

6. A gut microbiota typing device, characterized in that, include: The acquisition module is used to acquire gut microbiota sequencing data; the gut microbiota sequencing data includes gut microbiota 16S amplicon data and metagenomic sequencing data; The first relative abundance information determination module is used to perform quality control and species annotation analysis on the gut microbiota sequencing data to obtain the first relative abundance information of the sample gut microbiota. The screening module is used to screen gut microbiota characteristic data based on the first relative abundance information and the chi-square verification method. The prediction module is used to input the gut microbiota characteristic data into a preset gut type prediction model to predict the gut type. The first relative abundance information determination module includes: The first quality control unit is used to perform quality control on metagenomic sequencing data to remove adapters and filter out low-quality bases in the metagenomic sequencing data. The first removal unit is used to remove the host sequence from the quality-controlled metagenomic sequencing data to obtain the metagenomic DNA sequence. The first species annotation unit is used for species annotation of metagenomic DNA sequences; The correction unit is used to correct the annotation results and obtain the absolute abundance information of the gut microbiota. The first relative abundance information determination unit is used to extract the absolute abundance information of gut microbiota at the genus level and homogenize it to obtain the first relative abundance information of gut microbiota. The first relative abundance information determination module includes: The second quality control unit is used to merge paired-end sequence files if the gut microbiota 16S amplicon data are paired-end sequencing data, remove primers from the merged sequence files and perform quality control. The second removal unit is used to remove redundancy and chimerism from the quality-controlled sequence files and cluster them into operation classification units. The second species annotation unit is used to annotate the operational taxonomic units by comparing them with the database, so as to obtain the absolute abundance information of the gut microbiota. The second relative abundance information determination unit is used to extract the absolute abundance information of gut microbiota at the genus level and homogenize it to obtain the first relative abundance information of gut microbiota.

7. A gut microbiota typing device, characterized in that, Includes memory used to store computer programs; A processor, configured to implement the steps of the intestinal typing method based on the gut microbiota structure as described in any one of claims 1 to 5 when executing the computer program.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the intestinal typing method based on the intestinal microbiota structure as described in any one of claims 1 to 5.

Images